65 5 archive disk0/00/00/00/65 2009-04-06 19:10:22 2009-04-24 09:25:15 2009-04-06 19:10:22 conference_item show 0 Markines Benjamin Indiana University and Institute for Scientific Interchange Foundation Cattuto Ciro Institute for Scientific Interchange Foundation Menczer Filippo Indiana University and Institute for Scientific Interchange Foundation Benz Dominik University of Kassel Hotho Andreas University of Kassel Stumme Gerd University of Kassel Semantic/Data Web Evaluating Similarity Measures for Emergent Semantics of Social Tagging pub public paper Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We find that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity. 2009-04 641-641 18th International World Wide Web Conference Madrid, Spain April 20th-24th, 2009 conference TRUE 65 4 65 1 application/pdf en public
p641.pdf
published p641.pdf 978014 http://www2009.eprints.org/65/1/p641.pdf
282 3 65 2 application/pdf en public
www_2009.pdf
presentation www_2009.pdf 3677587 http://www2009.eprints.org/65/2/www_2009.pdf